Triple

T5154539
Position Surface form Disambiguated ID Type / Status
Subject Lyon tramway line T9 E116276 entity
Predicate isNumberedAs P22578 FINISHED
Object T9 in TCL system
T9 in the TCL system is a tram line designation used in the Lyon public transport network.
 E487753 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: T9 in TCL system | Statement: [Lyon tramway line T9, isNumberedAs, T9 in TCL system]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: T9 in TCL system
Context triple: [Lyon tramway line T9, isNumberedAs, T9 in TCL system]
  • A. Tcl
    Tcl (Tool Command Language) is a high-level, embeddable scripting language widely used for rapid prototyping, GUI development (often with Tk), and extending applications.
  • B. PL/Tcl
    PL/Tcl is a procedural language extension for PostgreSQL that allows writing database functions and triggers using the Tcl scripting language.
  • C. TCL fare system
    The TCL fare system is the integrated public transport ticketing and pricing network used across Lyon’s buses, trams, and metro services.
  • D. TCH
    TCH was the International Ice Hockey Federation (IIHF) country code used to represent the Czechoslovakia men's national ice hockey team in international competition.
  • E. TCC
    TCC is a public community college in Tallahassee, Florida, offering two-year degrees, workforce training, and transfer programs to four-year universities.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: T9 in TCL system
Triple: [Lyon tramway line T9, isNumberedAs, T9 in TCL system]
Generated description
T9 in the TCL system is a tram line designation used in the Lyon public transport network.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: T9 in TCL system
Target entity description: T9 in the TCL system is a tram line designation used in the Lyon public transport network.
  • A. Tcl
    Tcl (Tool Command Language) is a high-level, embeddable scripting language widely used for rapid prototyping, GUI development (often with Tk), and extending applications.
  • B. PL/Tcl
    PL/Tcl is a procedural language extension for PostgreSQL that allows writing database functions and triggers using the Tcl scripting language.
  • C. TCL fare system chosen
    The TCL fare system is the integrated public transport ticketing and pricing network used across Lyon’s buses, trams, and metro services.
  • D. TCH
    TCH was the International Ice Hockey Federation (IIHF) country code used to represent the Czechoslovakia men's national ice hockey team in international competition.
  • E. TCC
    TCC is a public community college in Tallahassee, Florida, offering two-year degrees, workforce training, and transfer programs to four-year universities.
  • F. None of above.

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69bd445d94788190b72e2cc563120995 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd78ddb01081909457ff4208eac4d7 completed March 20, 2026, 4:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69bed00e333881908487be6958e5133c completed March 21, 2026, 5:06 p.m.
NEDg Description generation batch_69bed358a1248190b97227404b3f2b31 completed March 21, 2026, 5:20 p.m.
NED2 Entity disambiguation (via description) batch_69bed3c470e48190998cacf9c0b42448 completed March 21, 2026, 5:22 p.m.
Created at: March 20, 2026, 1:44 p.m.